Azure Ai
Wire Azure AI services—especially Content Safety in Java—into a solo builder’s backend when you need moderation, blocklists, and SDK patterns without digging through full Microsoft docs.
Overview
azure-ai is an agent skill for the Build phase that gives solo builders Java SDK patterns for Azure AI Content Safety—clients, image moderation, blocklists, and moderation best practices—for apps integrating Azure AI ser
Install
npx skills add https://github.com/microsoft/azure-skills --skill azure-aiWhat is this skill?
- Maven dependency and Java builders for ContentSafetyClient and BlocklistClient
- Image moderation from bytes or blob URL with category-scoped requests
- Operational notes: blocklist propagation delay, severity thresholds, and parallel throughput
Adoption & trust: 375k installs on skills.sh; 1.2k GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You need to moderate user content with Azure AI Content Safety in Java but the SDK has split clients, awkward image payloads, and blocklist APIs that do not match the obvious typed-model examples.
Who is it for?
Indie developers adding UGC, chat, or upload features to a Java API or SaaS who already have an Azure subscription and want fast, correct Content Safety wiring.
Skip if: Teams on non-Java stacks only, builders who need a full Azure OpenAI or Cognitive Search tutorial in one skill, or anyone treating this as a substitute for reading current Azure SDK release notes and security review on t
When should I use this skill?
Use for Azure AI: Search, Speech, OpenAI, Document Intelligence.
What do I get? / Deliverables
You get install coordinates, working client builder snippets, and implementation habits for categories, severity cutoffs, parallel checks, and blocklist latency so moderation fits your backend cleanly.
- Maven dependency snippet and initialized ContentSafetyClient or BlocklistClient
- Image or text moderation request patterns aligned to your category and severity rules
- Implementation checklist for blocklist sync delay, parallel checks, and caching strategy
Recommended Skills
Journey fit
The skill is an Azure SDK integration reference for implementing AI platform features in application code, which belongs on the Build shelf where backends and third-party service hooks are assembled. Content Safety clients, credentials, endpoints, and blocklist APIs are external-service integrations, not frontend UI or generic PM docs.
How it compares
Use as a focused SDK integration skill—not an MCP server bridge and not a substitute for Azure’s full plugin docs when you need every API surface documented.
Common Questions / FAQ
Who is azure-ai for?
azure-ai is for solo and indie builders shipping products on Java who integrate Microsoft Azure AI—starting with Content Safety for text and image moderation—and want agent-guided SDK setup instead of piecing together fragments from search results.
When should I use azure-ai?
Use azure-ai during Build when you are hooking Azure endpoints into your backend (integrations subphase), and again in Ship when you are hardening user-facing flows that need blocklists and severity-based blocking before launch.
Is azure-ai safe to install?
Treat it like any third-party agent skill: review the Security Audits panel on this Prism page, confirm the source repository and license, and never let generated code embed Azure keys or endpoints you have not scoped with least privilege.
SKILL.md
READMESKILL.md - Azure Ai
# Azure AI Content Safety — Java SDK Quick Reference > Condensed from **azure-ai-contentsafety-java**. Full patterns (blocklist management, image moderation, 8-severity) > in the **azure-ai-contentsafety-java** plugin skill if installed. ## Install ```xml <dependency> <groupId>com.azure</groupId> <artifactId>azure-ai-contentsafety</artifactId> <version>1.1.0-beta.1</version> </dependency> ``` ## Quick Start ```java import com.azure.ai.contentsafety.ContentSafetyClient; import com.azure.ai.contentsafety.ContentSafetyClientBuilder; import com.azure.ai.contentsafety.BlocklistClient; import com.azure.ai.contentsafety.BlocklistClientBuilder; ContentSafetyClient client = new ContentSafetyClientBuilder() .endpoint(endpoint).credential(credential).buildClient(); ``` ## Non-Obvious Patterns - Two separate builders: `ContentSafetyClientBuilder` and `BlocklistClientBuilder` - Image from file: `new ContentSafetyImageData().setContent(BinaryData.fromBytes(bytes))` - Image from URL: `new ContentSafetyImageData().setBlobUrl(url)` - Blocklist create uses raw `BinaryData` + `RequestOptions` (not typed model) ## Best Practices 1. Blocklist changes take ~5 minutes to take effect 2. Only request needed categories to reduce latency 3. Typically block severity >= 4 for strict moderation 4. Process multiple items in parallel for throughput 5. Cache blocklist results where appropriate --- name: azure-ai description: "Use for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector search, hybrid search, semantic search, speech-to-text, text-to-speech, transcribe, OCR, convert text to speech." license: MIT metadata: author: Microsoft version: "1.1.1" --- # Azure AI Services ## Services | Service | Use When | MCP Tools | CLI | |---------|----------|-----------|-----| | AI Search | Full-text, vector, hybrid search | `azure__search` | `az search` | | Speech | Speech-to-text, text-to-speech | `azure__speech` | - | | OpenAI | GPT models, embeddings, DALL-E | - | `az cognitiveservices` | | Document Intelligence | Form extraction, OCR | - | - | ## MCP Server (Preferred) When Azure MCP is enabled: ### AI Search - `azure__search` with command `search_index_list` - List search indexes - `azure__search` with command `search_index_get` - Get index details - `azure__search` with command `search_query` - Query search index ### Speech - `azure__speech` with command `speech_transcribe` - Speech to text - `azure__speech` with command `speech_synthesize` - Text to speech **If Azure MCP is not enabled:** Run `/azure:setup` or enable via `/mcp`. ## AI Search Capabilities | Feature | Description | |---------|-------------| | Full-text search | Linguistic analysis, stemming | | Vector search | Semantic similarity with embeddings | | Hybrid search | Combined keyword + vector | | AI enrichment | Entity extraction, OCR, sentiment | ## Speech Capabilities | Feature | Description | |---------|-------------| | Speech-to-text | Real-time and batch transcription | | Text-to-speech | Neural voices, SSML support | | Speaker diarization | Identify who spoke when | | Custom models | Domain-specific vocabulary | ## SDK Quick References For programmatic access to these services, see the condensed SDK guides: - **AI Search**: [Python](references/sdk/azure-search-documents-py.md) | [TypeScript](references/sdk/azure-search-documents-ts.md) | [.NET](references/sdk/azure-search-documents-dotnet.md) - **OpenAI**: [.NET](references/sdk/azure-ai-openai-dotnet.md) - **Vision**: [Python](references/sdk/azure-ai-vision-imageanalysis-py.md) | [Java](references/sdk/azure-ai-vision-imageanalysis-java.md) - **Transcription**: [Python](references/sdk/azure-ai-transcription-py.md) - **Translation**: [Python](references/sdk/azure-ai-translation-text-py.md) | [TypeScript](references/sdk/azure-ai-translation-ts.md) - **Document Intelligence**